© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 30453
    Prev
    Next
    INDEX
    Explanations

    no followed by a noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arian
    -0.09
    oton
    -0.09
    ï¸
    -0.09
    rog
    -0.09
    terr
    -0.09
     unsupported
    -0.09
     invol
    -0.09
    esta
    -0.09
     presumably
    -0.09
     Ap
    -0.08
    POSITIVE LOGITS
     way
    0.21
     denying
    0.17
     doubt
    0.17
     escaping
    0.16
     reason
    0.15
     guarantee
    0.15
     telling
    0.15
     predicting
    0.15
     chance
    0.15
     need
    0.14
    Activations Density 0.035%

    No Known Activations